Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so "Effects: contact created" mostly restates them. The description does add one genuine rule (do not fabricate a contact, source is required), but it omits the consequence of idempotentHint=false — creating duplicates — even though a `hunt_check_duplicates` sibling exists, and it says nothing about the side effect of auto-creating the company noted in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The mandatory-source constraint is front-loaded, and the source explanation with three concrete examples earns its space. "Effects: contact created" is near-redundant given the annotations, and the parenthetical rule id (JH-2) is an internal reference with no explanation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, non-idempotent write with no output schema, the description should say what comes back (an id? the contact?), what happens on duplicate detection, and how the contact relates to the hunt pipeline. It covers the source requirement well but leaves the agent guessing on duplicate behavior and return value.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 30% across 10 parameters, so the description carries the burden — and it only fully explains `source`, with good examples of what counts. The other eight parameters (role, email, notes, phone, company, company_kind, linkedin_url, relationship) get nothing beyond their field names, and the two enums' business meaning is left entirely implicit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Add a person" is a clear verb+resource and the description immediately identifies the tool's subject as a contact/person record. It does not, however, distinguish itself from the very similar sibling `crm_add_contact`, nor from `hunt_apply` (which presumably also creates people in a pipeline), so the agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a strong guardrail ("Never invent a contact", source mandatory) and defines what a valid source is, which is real usage guidance. But it never says when to reach for this tool versus `crm_add_contact`, `hunt_check_duplicates`, or `hunt_update_contact` when the person already exists — the most likely selection error.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.